// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature +neon -target-feature +bf16 \
// RUN: -disable-O0-optnone -emit-llvm %s -o - | opt -S -mem2reg -instcombine | FileCheck %s

#include <arm_neon.h>

// CHECK-LABEL: @test_vbfdot_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R:%.*]], <4 x bfloat> [[A:%.*]], <4 x bfloat> [[B:%.*]]) [[ATTR3:#.*]]
// CHECK-NEXT:    ret <2 x float> [[VBFDOT3_I]]
//
float32x2_t test_vbfdot_f32(float32x2_t r, bfloat16x4_t a, bfloat16x4_t b) {
  return vbfdot_f32(r, a, b);
}

// CHECK-LABEL: @test_vbfdotq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFDOT3_I]]
//
float32x4_t test_vbfdotq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b){
  return vbfdotq_f32(r, a, b);
}

// CHECK-LABEL: @test_vbfdot_lane_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <4 x bfloat> [[B:%.*]] to <2 x float>
// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <2 x float> [[DOTCAST]], <2 x float> undef, <2 x i32> zeroinitializer
// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <2 x float> [[LANE]] to <4 x bfloat>
// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R:%.*]], <4 x bfloat> [[A:%.*]], <4 x bfloat> [[DOTCAST1]]) [[ATTR3]]
// CHECK-NEXT:    ret <2 x float> [[VBFDOT3_I]]
//
float32x2_t test_vbfdot_lane_f32(float32x2_t r, bfloat16x4_t a, bfloat16x4_t b){
  return vbfdot_lane_f32(r, a, b, 0);
}

// CHECK-LABEL: @test_vbfdotq_laneq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <4 x float>
// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <4 x float> [[DOTCAST]], <4 x float> undef, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <4 x float> [[LANE]] to <8 x bfloat>
// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[DOTCAST1]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFDOT3_I]]
//
float32x4_t test_vbfdotq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
  return vbfdotq_laneq_f32(r, a, b, 3);
}

// CHECK-LABEL: @test_vbfdot_laneq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <8 x bfloat> [[B:%.*]] to <4 x float>
// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <4 x float> [[DOTCAST]], <4 x float> undef, <2 x i32> <i32 3, i32 3>
// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <2 x float> [[LANE]] to <4 x bfloat>
// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <2 x float> @llvm.aarch64.neon.bfdot.v2f32.v4bf16(<2 x float> [[R:%.*]], <4 x bfloat> [[A:%.*]], <4 x bfloat> [[DOTCAST1]]) [[ATTR3]]
// CHECK-NEXT:    ret <2 x float> [[VBFDOT3_I]]
//
float32x2_t test_vbfdot_laneq_f32(float32x2_t r, bfloat16x4_t a, bfloat16x8_t b) {
  return vbfdot_laneq_f32(r, a, b, 3);
}

// CHECK-LABEL: @test_vbfdotq_lane_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTCAST:%.*]] = bitcast <4 x bfloat> [[B:%.*]] to <2 x float>
// CHECK-NEXT:    [[LANE:%.*]] = shufflevector <2 x float> [[DOTCAST]], <2 x float> undef, <4 x i32> zeroinitializer
// CHECK-NEXT:    [[DOTCAST1:%.*]] = bitcast <4 x float> [[LANE]] to <8 x bfloat>
// CHECK-NEXT:    [[VBFDOT3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfdot.v4f32.v8bf16(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[DOTCAST1]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFDOT3_I]]
//
float32x4_t test_vbfdotq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t b) {
  return vbfdotq_lane_f32(r, a, b, 0);
}

// CHECK-LABEL: @test_vbfmmlaq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VBFMMLAQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmmla(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMMLAQ_V3_I]]
//
float32x4_t test_vbfmmlaq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
  return vbfmmlaq_f32(r, a, b);
}

// CHECK-LABEL: @test_vbfmlalbq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VBFMLALBQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMLALBQ_V3_I]]
//
float32x4_t test_vbfmlalbq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
  return vbfmlalbq_f32(r, a, b);
}

// CHECK-LABEL: @test_vbfmlaltq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VBFMLALTQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[B:%.*]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMLALTQ_V3_I]]
//
float32x4_t test_vbfmlaltq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
  return vbfmlaltq_f32(r, a, b);
}

// CHECK-LABEL: @test_vbfmlalbq_lane_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <4 x bfloat> [[B:%.*]], <4 x bfloat> undef, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[VBFMLALBQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMLALBQ_V3_I]]
//
float32x4_t test_vbfmlalbq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t b) {
  return vbfmlalbq_lane_f32(r, a, b, 0);
}

// CHECK-LABEL: @test_vbfmlalbq_laneq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <8 x bfloat> [[B:%.*]], <8 x bfloat> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
// CHECK-NEXT:    [[VBFMLALBQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalb(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMLALBQ_V3_I]]
//
float32x4_t test_vbfmlalbq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
  return vbfmlalbq_laneq_f32(r, a, b, 3);
}

// CHECK-LABEL: @test_vbfmlaltq_lane_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <4 x bfloat> [[B:%.*]], <4 x bfloat> undef, <8 x i32> zeroinitializer
// CHECK-NEXT:    [[VBFMLALTQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMLALTQ_V3_I]]
//
float32x4_t test_vbfmlaltq_lane_f32(float32x4_t r, bfloat16x8_t a, bfloat16x4_t b) {
  return vbfmlaltq_lane_f32(r, a, b, 0);
}

// CHECK-LABEL: @test_vbfmlaltq_laneq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VECINIT35:%.*]] = shufflevector <8 x bfloat> [[B:%.*]], <8 x bfloat> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
// CHECK-NEXT:    [[VBFMLALTQ_V3_I:%.*]] = call <4 x float> @llvm.aarch64.neon.bfmlalt(<4 x float> [[R:%.*]], <8 x bfloat> [[A:%.*]], <8 x bfloat> [[VECINIT35]]) [[ATTR3]]
// CHECK-NEXT:    ret <4 x float> [[VBFMLALTQ_V3_I]]
//
float32x4_t test_vbfmlaltq_laneq_f32(float32x4_t r, bfloat16x8_t a, bfloat16x8_t b) {
  return vbfmlaltq_laneq_f32(r, a, b, 3);
}